Source: https://ailoot.ai/models/en/openai-gpt-5-4-image-2/
Canonical: https://ailoot.ai/models/en/openai-gpt-5-4-image-2/
Language: en

# OpenAI: GPT-5.4 Image 2

[Markdown](https://ailoot.ai/models/en/openai-gpt-5-4-image-2/index.md) · [JSON](https://ailoot.ai/models/en/openai-gpt-5-4-image-2/facts.json)

## [OpenAI: GPT-5.4 Image 2](https://ailoot.ai/models/en/openai-gpt-5-4-image-2/)

A workflow pairing GPT-5.4’s text reasoning with GPT Image 2’s image generation and editing. Use a written brief and visual references to develop an illustration or edit while keeping the text and image components’ roles distinct.

- [**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/openai-gpt-5-4-image-2/#method-0)
- [**Ailoot Ultra · Images** `POST /v1/images/generations` `openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/openai-gpt-5-4-image-2/#method-1)
- [**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/openai-gpt-5-4-image-2/#method-2)

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

GPT-5.4 Image 2 describes a workflow combining OpenAI’s GPT-5.4 text model with GPT Image 2 for image generation and editing. The components have different roles: GPT-5.4 can interpret a brief and develop the written instructions, while GPT Image 2 creates or modifies an image. GPT-5.4 accepts text and images and produces text; GPT Image 2 accepts text and image inputs and produces images.

For a new visual, describe its purpose, subject, composition, style and the details that matter to the result. An illustrative task is preparing an article illustration: define the idea the image should communicate, the intended crop and the space needed for accompanying page text. The written stage can organize these requirements into a clear brief. The image stage uses the prompt and any references to create the visual artifact.

For an edit, provide the source image and separate the requested changes from the elements to preserve. GPT Image 2 processes image inputs at high fidelity automatically, supporting detail-sensitive editing and reference workflows. The maker documents inpainting and reference-based image work. A mask can guide the area to edit, but GPT Image masking is prompt-based and may not follow the mask’s shape precisely. The documented mask flow requires the target image and mask to match in format and dimensions, with an alpha channel in the mask and files below 50 MB.

GPT Image 2 supports low, medium, high and automatic quality selection. Its custom sizes require both edges to be multiples of 16 pixels, neither edge to exceed 3,840 pixels, an aspect ratio no more extreme than 3:1 and a total size between 655,360 and 8,294,400 pixels. Documented examples include 1,024 × 1,024, 1,536 × 1,024, 2,048 × 2,048 and 3,840 × 2,160. Choose the dimensions for the destination rather than assuming every visual should be square. In the producer’s documented Image API output profile, PNG is the default format, with JPEG and WebP also available. JPEG and WebP support a compression setting from 0 to 100.

The text component has its own specification. GPT-5.4’s published context window is 1,050,000 tokens, its maximum output is 128,000 tokens and its knowledge cutoff is August 31, 2025. Its reasoning-effort choices are none, low, medium, high and xhigh, with none as the default. The producer lists image generation among GPT-5.4’s tools, while the Image API also provides separate generation and editing operations. These documented component roles do not turn the combined name into a new standalone model with one shared text-and-image limit.

The image guide describes limitations in precise text placement, recurring visual consistency and exact composition. Prepare short, clearly specified text when lettering matters, provide the relevant reference for a recurring subject and identify layout constraints explicitly. Review the generated or edited image against those requirements. A useful result can include the written brief, the image and a focused list of changes for the next edit, connecting the visual to the original editorial or product purpose.

Practical task

### Revise an editorial illustration crop

Technical example in English

```
Revise an editorial illustration crop

Edit the supplied article illustration for a landscape header. Preserve the central paper boat's shape, folded edges and blue color. Extend the calm water naturally to the left and leave that side visually quiet for page text added later. Keep the existing light direction and add no words, logos, people or extra boats.
```

#### Expected result

```
An edited landscape image with the original boat preserved and clear composition space on the left.
```

#### Check the result

```
Compare boat details and light direction with the source, and inspect the added water for repeated or distorted elements.
```

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions` `openai/gpt-5.4-image-2`

[`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=chat)

OpenAI /`openai/gpt-5.4-image-2`

### Overview

A workflow pairing GPT-5.4’s text reasoning with GPT Image 2’s image generation and editing. Use a written brief and visual references to develop an illustration or edit while keeping the text and image components’ roles distinct.

Accepted inputs

Text

Results

Text

### Available in Ailoot · inputs & methods

**Ailoot Ultra · OpenAI Chat** `POST /v1/chat/completions`

Input types

`text`

Output types

`text`

Output format

json or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits openai/gpt-5.4-image-2 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits Minimum items: 1 | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
| Field`messages[].content` | Type`string\|content_part[]\|null` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_calls` | Type`tool_call[]` | RequirementOptional | Values & limits | Default— |
| Field`messages[].tool_call_id` | Type`string` | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
| Field`messages[].name` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`messages[].reasoning_content` | Type`string` | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
| Field`messages[].reasoning_details` | Type`object\|array` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`max_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`max_completion_tokens` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |
| Field`stream_options.include_usage` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`temperature` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`top_p` | Type`number` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`stop` | Type`string\|string[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools` | Type`function_tool[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`tools[].type` | Type`string` | RequirementOptional | Values & limits function Model-specific | Default— |
| Field`tools[].function.name` | Type`string` | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
| Field`tools[].function.description` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`tools[].function.parameters` | Type`JSON_schema` | RequirementOptional | Values & limits | Default— |
| Field`tool_choice` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`parallel_tool_calls` | Type`boolean` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`response_format` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning_effort` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`reasoning` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`service_tier` | Type`string` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`instructions` | Type`string` | RequirementOptional | Values & limits Compatibility field | Default— |
| Field`functions` | Type`function[]` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`function_call` | Type`string\|object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`prompt_cache_options` | Type`object` | RequirementOptional | Values & limits Model-specific | Default— |
| Field`modalities` | Type`string[]` | RequirementOptional | Values & limits text | Default— |
| Field`provider` | Type`object` | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
| Field`cache_control.ttl` | Type`string` | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |

Input material combinations

**Text** · UTF8 text

`messages[].content`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages |
| Parameter`material_types` | Contracttext |
| Parameter`messages` | Contractmessage array with role/content shape |
| Parameter`file_material` | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
| Parameter`optional_controls` | Contractstream, temperature, top\_p, stop, max\_tokens, max\_completion\_tokens, reasoning, response\_format, tools, tool\_choice |
| Parameter`control_scope` | Contractmodel-specific; user function tools differ from hosted tools |
| Parameter`output_modalities` | Contracttext |
| Parameter`hosted_operations` | Contractfalse |
| Parameter`multimodal_input_binding` | Contractnull |

Lifecycle: `synchronous_or_streamed`

Send exact model ID with messages.

Context length is not an output cap.

A text file may supply literal text; image/audio/file-object inputs need exact binding.

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · medium

Standard rate When reasoning effort is medium

Reasoning effort · none

Standard rate When reasoning effort is none

Reasoning effort · xhigh

Standard rate When reasoning effort is xhigh

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.016** / 1K tokens Output · Output tokens **$0.03** / 1K tokens Input · Cache read **$0.004** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens Output · Image output tokens **$0.06** / 1K image tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.016** / 1K tokens Output · Output tokens **$0.03** / 1K tokens Input · Cache read **$0.004** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

OpenAI: GPT-5.4 Image 2

#### Prices by configuration

| Configuration | Billing conditions | Charge |
| --- | --- | --- |
| ConfigurationOpenAI: GPT-5.4 Image 2 · Default configuration | Billing conditionsDefault configuration | Charge Input · Input tokens **$0.016** / 1K tokens Output · Output tokens **$0.03** / 1K tokens Output · Output image **$0.06** / 1K tokens Output · Web search **$0.02** per search Input · Cache read **$0.004** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · OpenAI Chat

curlPython SDKPython stream

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "openai/gpt-5.4-image-2", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
    if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
```

```python
from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model='openai/gpt-5.4-image-2',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(result.to_dict(mode="json"))
```

```python
from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        ext = "png" if raw.startswith(b"\x89PNG\r\n\x1a\n") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='openai/gpt-5.4-image-2',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")
```

### Receive and save results

#### Ailoot Ultra · OpenAI Chat

json or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`choices[].index` | Typeinteger |
| Field`choices[].message.content` | Typestring\|null |
| Field`choices[].message.tool_calls` | Typetool\_call\[\] |
| Field`choices[].message.reasoning_content` | Typestring |
| Field`choices[].message.reasoning_details` | Typeobject\|array |
| Field`choices[].finish_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

**Ailoot Ultra** [`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=chat)

#### Method path aliases

`/v1/images`

#### Related caller IDs

[`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=chat)

**Ailoot Ultra · Images** `POST /v1/images/generations` `openai/gpt-5.4-image-2`

[`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=images)

OpenAI /`openai/gpt-5.4-image-2`

### Overview

A workflow pairing GPT-5.4’s text reasoning with GPT Image 2’s image generation and editing. Use a written brief and visual references to develop an illustration or edit while keeping the text and image components’ roles distinct.

Accepted inputs

Text · Images

Results

Images

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Images** `POST /v1/images/generations`

Input types

`text`, `image`

Output types

`image`

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits openai/gpt-5.4-image-2 | Default— |
| Field`prompt` | Type`string` | RequirementRequired | Values & limits Minimum length: 1 | Default— |
| Field`aspect_ratio` | Type`string` | RequirementOptional | Values & limits 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, auto | Default— |
| Field`quality` | Type`string` | RequirementOptional | Values & limits auto, low, medium, high | Default— |
| Field`background` | Type`string` | RequirementOptional | Values & limits auto, opaque | Default— |
| Field`n` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 Maximum: 10 | Default— |
| Field`input_references` | Type`array` | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 16 | Default— |
| Field`output_compression` | Type`integer` | RequirementOptional | Values & limits Minimum: 0 Maximum: 100 | Default— |
| Field`provider` | Type`object` | RequirementOptional | Values & limits | Default— |

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, prompt |
| Parameter`material_types` | Contracttext, image |

Lifecycle: `synchronous_result_then_owned_library`

`GET /v1/media/tasks/{task_id}` · actual returned task\_id or media library record

`GET /v1/media/assets/{asset_id}/content`

`GET /v1/media/assets`

`GET /v1/media/assets/{asset_id}`

### Pricing

##### How the final charge is calculated

The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Not specified When fast mode is selected

Flex mode

Not specified When flex mode is selected

Maximum reasoning effort

Not specified When maximum reasoning effort uses the default adjustment

#### Estimated rates for comparison

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Forecast quantity | Charge |
| --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge Input · Input tokens · Estimate for comparison only **—** / 1K tokens Output · Output tokens · Estimate for comparison only **—** / 1K tokens Input · Cache read · Estimate for comparison only **—** / 1K tokens Input · Cache write · Estimate for comparison only **—** / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only **—** / 1K tokens |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only **$0.24576** estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Images

curl

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p={'model': 'openai/gpt-5.4-image-2', 'prompt': 'a red panda astronaut floating in space, studio lighting'}

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json, os, subprocess
from pathlib import Path
from urllib.parse import urlsplit, urljoin

def save_images(items):
    if not items: raise SystemExit("No completed images; retain the full response")
    for index, item in enumerate(items):
        encoded=item.get("b64_json")
        uri=item.get("url", "")
        if not encoded and uri.startswith("data:image/"):
            header, separator, encoded=uri.partition(",")
            if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")
        if encoded:
            raw=base64.b64decode(encoded,validate=True)
        elif uri:
            uri=urljoin("https://api.ailoot.ai",uri)
            parsed=urlsplit(uri)
            if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:
                raise SystemExit("Invalid returned image URL")
            owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")
            args=["curl","--fail-with-body","--silent","--show-error",uri]
            if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]
            temporary=Path(f"image-{index}.bin")
            subprocess.run(args+["-o",str(temporary)],check=True)
            raw=temporary.read_bytes()
            temporary.unlink()
        else: raise SystemExit("Image has neither bytes nor URL")
        if not raw: raise SystemExit("Empty image result")
        ext="png" if raw.startswith(b"\x89PNG") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"
        Path(f"image-{index}.{ext}").write_bytes(raw)
    print("Every returned image saved; complete response metadata retained")
save_images(json.loads(Path("result.json").read_text())["data"])
PY_RESULT
```

### Receive and save results

#### Ailoot Ultra · Images

Download each returned image or save its Base64 contents

- `GET /v1/media/tasks/{task_id}`
- `GET /v1/media/assets/{asset_id}/content`
- `GET /v1/media/assets`
- `GET /v1/media/assets/{asset_id}`

Other content reads

Read existing owned assets

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \
  -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json
# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.
```

##### Keep all completed results

Save every completed image; retrieve each returned URL or decode its Base64 contents.

Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.

##### If the original response needs checking

Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task\_id/asset\_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.

Response fields

| Field | Type |
| --- | --- |
| Field`created` | Type |
| Field`data[].url` | Type |
| Field`data[].b64_json` | Type |
| Field`usage` | Type |

### Aliases

#### Model aliases

**Ailoot Ultra** [`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=images)

#### Method path aliases

`/v1/images`

#### Related caller IDs

[`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=images)

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages` `openai/gpt-5.4-image-2`

[`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=messages)

OpenAI /`openai/gpt-5.4-image-2`

### Overview

A workflow pairing GPT-5.4’s text reasoning with GPT Image 2’s image generation and editing. Use a written brief and visual references to develop an illustration or edit while keeping the text and image components’ roles distinct.

Accepted inputs

Text

Results

json · sse

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Anthropic Messages** `POST /v1/messages`

Input types

`text`

Output types

`json`, `sse`

Output format

JSON or SSE

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits openai/gpt-5.4-image-2 | Default— |
| Field`messages` | Type`message[]` | RequirementRequired | Values & limits | Default— |
| Field`messages[].role` | Type`string` | RequirementRequired | Values & limits user, assistant | Default— |
| Field`messages[].content` | Type`string` | RequirementRequired | Values & limits | Default— |
| Field`max_tokens` | Type`integer` | RequirementRequired | Values & limits | Default— |
| Field`stream` | Type`boolean` | RequirementOptional | Values & limits | Defaultfalse |

Input material combinations

**Text** · UTF-8 text

`messages[].content string`

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, messages, max\_tokens |
| Parameter`optional_controls` | Contractstream |
| Parameter`material_types` | Contracttext |
| Parameter`text_file_material` | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |

Lifecycle: `synchronous_or_streamed`

### Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Standard rate When fast mode is selected

Flex mode

Standard rate When flex mode is selected

Maximum reasoning effort

Standard rate When maximum reasoning effort uses the default adjustment

Reasoning effort · high

Standard rate When reasoning effort is high

Reasoning effort · low

Standard rate When reasoning effort is low

Reasoning effort · medium

Standard rate When reasoning effort is medium

Reasoning effort · none

Standard rate When reasoning effort is none

Reasoning effort · xhigh

Standard rate When reasoning effort is xhigh

#### Ailoot rates

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
| --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.016** / 1K tokens Output · Output tokens **$0.03** / 1K tokens Input · Cache read **$0.004** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens Output · Image output tokens **$0.06** / 1K image tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens **$0.016** / 1K tokens Output · Output tokens **$0.03** / 1K tokens Input · Cache read **$0.004** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

### Example requests

#### Ailoot Ultra · Anthropic Messages

Complete minimal JSON bodycurl · use your UTF-8 documentPython · save the complete result

```json
{
  "model": "openai/gpt-5.4-image-2",
  "max_tokens": 128,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the incident report."
    }
  ],
  "stream": false
}
```

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'openai/gpt-5.4-image-2', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
```

```python
import json, os
from pathlib import Path

source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
    raise SystemExit('Choose a document containing text')
payload = {'model': 'openai/gpt-5.4-image-2', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError

api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
    raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
    with urlopen(request, timeout=120) as response:
        raw = response.read()
        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
    Path('result.json').write_bytes(error.read())
    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
    raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path

result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
```

### Receive and save results

#### Ailoot Ultra · Anthropic Messages

JSON or SSE

##### Keep all completed results

Keep every complete returned response, file and content part.

Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.

##### If the original response needs checking

Keep request/response IDs and headers. No generic text job retrieval URL is supplied.

Response fields

| Field | Type |
| --- | --- |
| Field`id` | Typestring |
| Field`model` | Typestring |
| Field`content[]` | Typetext\|thinking\|tool\_use\|other content block |
| Field`stop_reason` | Typestring\|null |
| Field`usage` | Typeobject |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response400 · `invalid_request_error` | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |

### Aliases

#### Model aliases

**Ailoot Ultra** [`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=messages)

#### Method path aliases

`/v1/images`

#### Related caller IDs

[`openai/gpt-5.4-image-2`](https://ailoot.ai/models/en/#m=openai%2Fgpt-5.4-image-2&route=Ultra&caller=openai%2Fgpt-5.4-image-2&fmt=messages)

FAQ · OpenAI: GPT-5.4 Image 2

What inputs and results are available?

`POST /v1/chat/completions` · `openai/gpt-5.4-image-2`: `text` → `text` `POST /v1/images/generations` · `openai/gpt-5.4-image-2`: `text`, `image` → `image` `POST /v1/messages` · `openai/gpt-5.4-image-2`: `text` → `json`, `sse`

Which fields does the request use?

`POST /v1/chat/completions` · `openai/gpt-5.4-image-2`: `model`, `messages`, `stream`, `modalities`, `provider` `POST /v1/images/generations` · `openai/gpt-5.4-image-2`: `model`, `prompt`, `aspect_ratio`, `quality`, `background`, `n`, `input_references`, `output_compression`, `provider` `POST /v1/messages` · `openai/gpt-5.4-image-2`: `model`, `messages`, `max_tokens`, `stream`

What limits apply?

`POST /v1/chat/completions` · `openai/gpt-5.4-image-2`: `messages.min_items`: `1` `POST /v1/images/generations` · `openai/gpt-5.4-image-2`: `n.minimum`: `1`; `n.maximum`: `10`; `output_compression.minimum`: `0`; `output_compression.maximum`: `100`

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

## The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

## Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription

Choose a discounted plan for your regular requests.

Promo code: up to 50% off

Enter your code at checkout. The price updates to reflect the current promotion.

Spending in your history

The model, tokens and amount are recorded for each request.

[Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/)

## Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application

Add text, image, video and audio generation to paid features in your service.

Reseller licence

Send a description of your project and how you provide access. Request written terms for use and resale.

Documents on the website

The service offer, licence agreement and data processing policy are available before you connect.

[Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.